EUVIMEDEUVIMED entdecken
Crossref

Evaluation of a commercial deep-learning-based contouring software for CT-based gynecological brachytherapy

Haechan J Yang, John Patrick, Jason Vickress, David D'Souza, Vikram Velker, Lucas Mendez, Maria Mansur Starling, Aaron Fenster, Douglas Hoover

Brachytherapy · 2026

DOI: 10.1016/j.brachy.2025.08.005 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Brachytherapy, 2026. Verfasst von Haechan J Yang und 8 weiteren Autor:innen. Beteiligte Einrichtung: Schulich School of Medicine and Dentistry, Western University, London, Ontario, Canada; Department of Medical Biophysics, Western University, London,…. Hauptthemen laut MEDLINE: Brachytherapy, Deep Learning, Genital Neoplasms, Female, Tomography, X-Ray Computed. Die Arbeit nennt 25 Literaturangaben. Gefördert von: London Health Sciences Foundation, Ontario Institute for Cancer Research, Canadian Institutes of Health Research.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PURPOSE: To evaluate a commercial deep-learning based auto-contouring software specifically trained for high-dose-rate gynecological brachytherapy. METHODS AND MATERIALS: We collected CT images from 30 patients treated with gynecological brachytherapy (19.5-28 Gy in 3-4 fractions) at our institution from January 2018 to December 2022. Clinical and artificial intelligence (AI) generated contours for bladder, bowel, rectum, and sigmoid were obtained. Five patients were randomly selected from the test set and manually re-contoured by 4 radiation oncologists. Contouring was repeated 2 weeks later using AI contours as the starting point ("AI-assisted" approach). Comparisons amongst clinical, AI, AI-assisted, and manual retrospective contours were made using various metrics, including Dice similarity coefficient (DSC) and unsigned D2cc difference. RESULTS: Between clinical and AI contours, DSC was 0.92, 0.79, 0.62, 0.66, for bladder, rectum, sigmoid, and bowel, respectively. Rectum and sigmoid had the lowest median unsigned D2cc difference of 0.20 and 0.21 Gy/fraction respectively between clinical and AI contours, while bowel had the largest median difference of 0.38 Gy/fraction. Agreement between fully automated AI and clinical contours was generally not different compared to agreement between AI-assisted and clinical contours. AI-assisted interobserver agreement was better than manual interobserver agreement for all organs and metrics. The median time to contour all organs for manual and AI-assisted approaches was 14.8 and 6.9 minutes/patient (p < 0.001), respectively. CONCLUSIONS: The agreement between AI or AI-assisted contours against the clinical contours was similar to manual interobserver agreement. Implementation of the AI-assisted contouring approach could enhance clinical workflow by decreasing both contouring time and interobserver variability.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

BrachytherapyDeep LearningGenital Neoplasms, FemaleTomography, X-Ray ComputedRadiotherapy Planning, Computer-AssistedSoftwareHumansFemaleRetrospective StudiesRectumUrinary BladderRadiotherapy DosageOrgans at Risk

Stichwörter der Autor:innen

Artificial intelligenceAuto-segmentationGynecological cancerHigh dose rate brachytherapy

Autor:innen und Institutionen

  • Schulich School of Medicine and Dentistry, Western University, London, Ontario, Canada; Department of Medical Biophysics, Western University, London, Ontario, Canada; Robarts Research Institute, Western University, Lond…
  • Department of Radiation Oncology, London Health Sciences Centre, London, Ontario, Canada; Department of Oncology, Western University, London, Ontario, Canada; Department of Medical Biophysics, Western University, London…
  • Department of Radiation Oncology, London Health Sciences Centre, London, Ontario, Canada; Department of Oncology, Western University, London, Ontario, Canada.
  • Department of Radiation Oncology, London Health Sciences Centre, London, Ontario, Canada.
  • Department of Medical Biophysics, Western University, London, Ontario, Canada; Robarts Research Institute, Western University, London, Ontario, Canada.

Förderung

  • London Health Sciences Foundation
  • Ontario Institute for Cancer Research
  • Canadian Institutes of Health Research
  • Natural Sciences and Engineering Research Council of Canada

Zitieren

APA

Yang, H. J., Patrick, J., Vickress, J., D'Souza, D., Velker, V., Mendez, L., Starling, M. M., Fenster, A., & Hoover, D. (2026). Evaluation of a commercial deep-learning-based contouring software for CT-based gynecological brachytherapy. Brachytherapy. https://doi.org/10.1016/j.brachy.2025.08.005

Vancouver

Yang HJ, Patrick J, Vickress J, D'Souza D, Velker V, Mendez L, et al. Evaluation of a commercial deep-learning-based contouring software for CT-based gynecological brachytherapy. Brachytherapy. 2026. doi:10.1016/j.brachy.2025.08.005

BibTeX
@article{Yang2026,
  author = {Yang, Haechan J and Patrick, John and Vickress, Jason and D'Souza, David and Velker, Vikram and Mendez, Lucas and Starling, Maria Mansur and Fenster, Aaron and Hoover, Douglas},
  title = {Evaluation of a commercial deep-learning-based contouring software for CT-based gynecological brachytherapy},
  journal = {Brachytherapy},
  year = {2026},
  doi = {10.1016/j.brachy.2025.08.005}
}
Kostenlos starten →